{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/p-generalized-probit-regression-and-scalable","title":"$p$-Generalized Probit Regression and Scalable Maximum Likelihood Estimation via Sketching and Coresets","arxiv_id":"2203.13568","date":"2022-03-25","proceeding":null,"authors":["Alexander Munteanu","Simon Omlor","Christian Peters"],"abstract":"We study the $p$-generalized probit regression model, which is a generalized linear model for binary responses. It extends the standard probit model by replacing its link function, the standard normal cdf, by a $p$-generalized normal distribution for $p\\in[1, \\infty)$. The $p$-generalized normal distributions \\citep{Sub23} are of special interest in statistical modeling because they fit much more flexibly to data. Their tail behavior can be controlled by choice of the parameter $p$, which influences the model's sensitivity to outliers. Special cases include the Laplace, the Gaussian, and the uniform distributions. We further show how the maximum likelihood estimator for $p$-generalized probit regression can be approximated efficiently up to a factor of $(1+\\varepsilon)$ on large data by combining sketching techniques with importance subsampling to obtain a small data summary called coreset.","url_abs":"https://arxiv.org/abs/2203.13568v1","url_pdf":"https://arxiv.org/pdf/2203.13568v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"p-generalized-probit-regression-and-scalable","repo_url":"https://github.com/cxan96/efficient-probit-regression","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"regression-1","task_name":"regression"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2203.13568","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.13568"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/cxan96/efficient-probit-regression","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":10},"by_repo_kind":{"official":{"samples":10,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"6f87712ad48e6258","entry":"add_intercept","repo":"cxan96/efficient-probit-regression","repo_kind":"official","path":"efficient_probit_regression/datasets.py","file_url":"https://github.com/cxan96/efficient-probit-regression/blob/HEAD/efficient_probit_regression/datasets.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6f87712ad48e6258"}},{"code_sha256_prefix":"119b435476768082","entry":"compute_leverage_scores","repo":"cxan96/efficient-probit-regression","repo_kind":"official","path":"efficient_probit_regression/sampling.py","file_url":"https://github.com/cxan96/efficient-probit-regression/blob/HEAD/efficient_probit_regression/sampling.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"119b435476768082"}},{"code_sha256_prefix":"c758f15b061b5e94","entry":"fast_QR","repo":"cxan96/efficient-probit-regression","repo_kind":"official","path":"efficient_probit_regression/sampling.py","file_url":"https://github.com/cxan96/efficient-probit-regression/blob/HEAD/efficient_probit_regression/sampling.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c758f15b061b5e94"}},{"code_sha256_prefix":"c8c367cbc656fc9a","entry":"gaussian_kernel","repo":"cxan96/efficient-probit-regression","repo_kind":"official","path":"efficient_probit_regression/metrics.py","file_url":"https://github.com/cxan96/efficient-probit-regression/blob/HEAD/efficient_probit_regression/metrics.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c8c367cbc656fc9a"}},{"code_sha256_prefix":"d052868fdd91425f","entry":"get_results_dir_p","repo":"cxan96/efficient-probit-regression","repo_kind":"official","path":"efficient_probit_regression/settings.py","file_url":"https://github.com/cxan96/efficient-probit-regression/blob/HEAD/efficient_probit_regression/settings.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d052868fdd91425f"}},{"code_sha256_prefix":"3c164ca8797dd680","entry":"mmd","repo":"cxan96/efficient-probit-regression","repo_kind":"official","path":"efficient_probit_regression/metrics.py","file_url":"https://github.com/cxan96/efficient-probit-regression/blob/HEAD/efficient_probit_regression/metrics.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3c164ca8797dd680"}},{"code_sha256_prefix":"bba3230f0550e694","entry":"p_gen_norm_cdf","repo":"cxan96/efficient-probit-regression","repo_kind":"official","path":"efficient_probit_regression/probit_model.py","file_url":"https://github.com/cxan96/efficient-probit-regression/blob/HEAD/efficient_probit_regression/probit_model.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bba3230f0550e694"}},{"code_sha256_prefix":"0b3d8671a851a6d8","entry":"p_gen_norm_pdf","repo":"cxan96/efficient-probit-regression","repo_kind":"official","path":"efficient_probit_regression/probit_model.py","file_url":"https://github.com/cxan96/efficient-probit-regression/blob/HEAD/efficient_probit_regression/probit_model.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0b3d8671a851a6d8"}},{"code_sha256_prefix":"cb9a66905aff629b","entry":"polynomial_kernel","repo":"cxan96/efficient-probit-regression","repo_kind":"official","path":"efficient_probit_regression/metrics.py","file_url":"https://github.com/cxan96/efficient-probit-regression/blob/HEAD/efficient_probit_regression/metrics.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cb9a66905aff629b"}},{"code_sha256_prefix":"02e04515634f9ff2","entry":"uniform_sampling","repo":"cxan96/efficient-probit-regression","repo_kind":"official","path":"efficient_probit_regression/sampling.py","file_url":"https://github.com/cxan96/efficient-probit-regression/blob/HEAD/efficient_probit_regression/sampling.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"02e04515634f9ff2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}